Abstract: Considering the fact that the present sales forecasting model can′t respond to the versatile and changing market and the needs of distributors in time,an appropriate CURE algorithm and C4.5 decision tree method is adopted to establish a new costume sales forecasting model.The CURE algorithm carries out grouping of similar items in terms of sales prospect,and the C4.5 decision tree finds understandable links between these clusters and selected descriptive criteria.Based on the test of 568 historical sales data and 326 new data,the performance efficiency of forecasting model is analyzed.Finally,aiming at the classification error of forecasting model,a further improvement method is given.